first add

lm_eval/datasets/logiqa/dataset_infos.json

+{"logiqa": {"description": "LogiQA is a dataset for testing human logical reasoning. It consists of 8,678 QA\ninstances, covering multiple types of deductive reasoning. Results show that state-\nof-the-art neural models perform by far worse than human ceiling. The dataset can\nalso serve as a benchmark for reinvestigating logical AI under the deep learning\nNLP setting.\n", "citation": "@misc{liu2020logiqa,\n    title={LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning}, \n    author={Jian Liu and Leyang Cui and Hanmeng Liu and Dandan Huang and Yile Wang and Yue Zhang},\n    year={2020},\n    eprint={2007.08124},\n    archivePrefix={arXiv},\n    primaryClass={cs.CL}\n}\n", "homepage": "https://github.com/lgw863/LogiQA-dataset", "license": "", "features": {"label": {"dtype": "string", "id": null, "_type": "Value"}, "context": {"dtype": "string", "id": null, "_type": "Value"}, "question": {"dtype": "string", "id": null, "_type": "Value"}, "options": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "logiqa", "config_name": "logiqa", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"train": {"name": "train", "num_bytes": 6419852, "num_examples": 7376, "dataset_name": "logiqa"}, "test": {"name": "test", "num_bytes": 571705, "num_examples": 651, "dataset_name": "logiqa"}, "validation": {"name": "validation", "num_bytes": 562437, "num_examples": 651, "dataset_name": "logiqa"}}, "download_checksums": {"https://raw.githubusercontent.com/lgw863/LogiQA-dataset/master/Train.txt": {"num_bytes": 6281272, "checksum": "7d5bb1f58278e33b395744cd2ad8d7600faa0b3c4d615c659a44ec1181d759fa"}, "https://raw.githubusercontent.com/lgw863/LogiQA-dataset/master/Test.txt": {"num_bytes": 559060, "checksum": "359acb78c37802208f7fde9e2f6574b8526527c63d6a336f90a53f1932cb4701"}, "https://raw.githubusercontent.com/lgw863/LogiQA-dataset/master/Eval.txt": {"num_bytes": 550021, "checksum": "4c49e6753b7262c001506b9151135abf722247035ab075dad93acdea5789c01f"}}, "download_size": 7390353, "post_processing_size": null, "dataset_size": 7553994, "size_in_bytes": 14944347}}

lm_eval/datasets/mutual/dataset_infos.json

+{"mutual": {"description": "MuTual is a retrieval-based dataset for multi-turn dialogue reasoning, which is\nmodified from Chinese high school English listening comprehension test data.\n\nThe MuTual dataset.", "citation": "@inproceedings{mutual,\n    title = \"MuTual: A Dataset for Multi-Turn Dialogue Reasoning\",\n    author = \"Cui, Leyang  and Wu, Yu and Liu, Shujie and Zhang, Yue and Zhou, Ming\" ,\n    booktitle = \"Proceedings of the 58th Conference of the Association for Computational Linguistics\",\n    year = \"2020\",\n    publisher = \"Association for Computational Linguistics\",\n}\n", "homepage": "https://github.com/Nealcly/MuTual", "license": "", "features": {"answers": {"dtype": "string", "id": null, "_type": "Value"}, "options": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "article": {"dtype": "string", "id": null, "_type": "Value"}, "id": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "mutual", "config_name": "mutual", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"train": {"name": "train", "num_bytes": 5141602, "num_examples": 7088, "dataset_name": "mutual"}, "test": {"name": "test", "num_bytes": 634396, "num_examples": 886, "dataset_name": "mutual"}, "validation": {"name": "validation", "num_bytes": 624271, "num_examples": 886, "dataset_name": "mutual"}}, "download_checksums": {"https://github.com/Nealcly/MuTual/archive/master.zip": {"num_bytes": 10997878, "checksum": "bb325cf6c672f0f02699993a37138b0fa0af6fcfc77ec81dfbe46add4d7b29f9"}}, "download_size": 10997878, "post_processing_size": null, "dataset_size": 6400269, "size_in_bytes": 17398147}, "mutual_plus": {"description": "MuTual is a retrieval-based dataset for multi-turn dialogue reasoning, which is\nmodified from Chinese high school English listening comprehension test data.\n\nMuTualPlus is a more difficult MuTual that replaces positive responses with a safe responses.", "citation": "@inproceedings{mutual,\n    title = \"MuTual: A Dataset for Multi-Turn Dialogue Reasoning\",\n    author = \"Cui, Leyang  and Wu, Yu and Liu, Shujie and Zhang, Yue and Zhou, Ming\" ,\n    booktitle = \"Proceedings of the 58th Conference of the Association for Computational Linguistics\",\n    year = \"2020\",\n    publisher = \"Association for Computational Linguistics\",\n}\n", "homepage": "https://github.com/Nealcly/MuTual", "license": "", "features": {"answers": {"dtype": "string", "id": null, "_type": "Value"}, "options": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "article": {"dtype": "string", "id": null, "_type": "Value"}, "id": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "mutual", "config_name": "mutual_plus", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"train": {"name": "train", "num_bytes": 4921179, "num_examples": 7088, "dataset_name": "mutual"}, "test": {"name": "test", "num_bytes": 606620, "num_examples": 886, "dataset_name": "mutual"}, "validation": {"name": "validation", "num_bytes": 597340, "num_examples": 886, "dataset_name": "mutual"}}, "download_checksums": {"https://github.com/Nealcly/MuTual/archive/master.zip": {"num_bytes": 10997878, "checksum": "bb325cf6c672f0f02699993a37138b0fa0af6fcfc77ec81dfbe46add4d7b29f9"}}, "download_size": 10997878, "post_processing_size": null, "dataset_size": 6125139, "size_in_bytes": 17123017}}

lm_eval/datasets/quac/dataset_infos.json

+{"quac": {"description": "Question Answering in Context (QuAC) is a dataset for modeling, understanding, and \nparticipating in information seeking dialog. Data instances consist of an interactive\ndialog between two crowd workers: (1) a student who poses a sequence of freeform\nquestions to learn as much as possible about a hidden Wikipedia text, and (2)\na teacher who answers the questions by providing short excerpts (spans) from the text.\n", "citation": "@article{choi2018quac,\n    title={Quac: Question answering in context},\n    author={Choi, Eunsol and He, He and Iyyer, Mohit and Yatskar, Mark and Yih, Wen-tau and Choi, Yejin and Liang, Percy and Zettlemoyer, Luke},\n    journal={arXiv preprint arXiv:1808.07036},\n    year={2018}\n}\n", "homepage": "https://quac.ai/", "license": "", "features": {"title": {"dtype": "string", "id": null, "_type": "Value"}, "section_title": {"dtype": "string", "id": null, "_type": "Value"}, "paragraph": {"dtype": "string", "id": null, "_type": "Value"}, "question": {"dtype": "string", "id": null, "_type": "Value"}, "answer": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "quac", "config_name": "quac", "version": {"version_str": "1.1.0", "description": null, "major": 1, "minor": 1, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 212391958, "num_examples": 83568, "dataset_name": "quac"}, "validation": {"name": "validation", "num_bytes": 20678483, "num_examples": 7354, "dataset_name": "quac"}}, "download_checksums": {"https://s3.amazonaws.com/my89public/quac/train_v0.2.json": {"num_bytes": 68114819, "checksum": "ff5cca5a2e4b4d1cb5b5ced68b9fce88394ef6d93117426d6d4baafbcc05c56a"}, "https://s3.amazonaws.com/my89public/quac/val_v0.2.json": {"num_bytes": 8929167, "checksum": "09e622916280ba04c9352acb1bc5bbe80f11a2598f6f34e934c51d9e6570f378"}}, "download_size": 77043986, "post_processing_size": null, "dataset_size": 233070441, "size_in_bytes": 310114427}}

lm_eval/datasets/unscramble/dataset_infos.json

+{"mid_word_1_anagrams": {"description": "Unscramble is a small battery of 5 \u201ccharacter manipulation\u201d tasks. Each task\ninvolves giving the model a word distorted by some combination of scrambling,\naddition, or deletion of characters, and asking it to recover the original word.\n", "citation": "@inproceedings{NEURIPS2020_1457c0d6,\n    author = {Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and Agarwal, Sandhini and Herbert-Voss, Ariel and Krueger, Gretchen and Henighan, Tom and Child, Rewon and Ramesh, Aditya and Ziegler, Daniel and Wu, Jeffrey and Winter, Clemens and Hesse, Chris and Chen, Mark and Sigler, Eric and Litwin, Mateusz and Gray, Scott and Chess, Benjamin and Clark, Jack and Berner, Christopher and McCandlish, Sam and Radford, Alec and Sutskever, Ilya and Amodei, Dario},\n    booktitle = {Advances in Neural Information Processing Systems},\n    editor = {H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin},\n    pages = {1877--1901},\n    publisher = {Curran Associates, Inc.},\n    title = {Language Models are Few-Shot Learners},\n    url = {https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf},\n    volume = {33},\n    year = {2020}\n}\n", "homepage": "https://github.com/openai/gpt-3/tree/master/data", "license": "", "features": {"context": {"dtype": "string", "id": null, "_type": "Value"}, "completion": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "unscramble", "config_name": "mid_word_1_anagrams", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"validation": {"name": "validation", "num_bytes": 271516, "num_examples": 10000, "dataset_name": "unscramble"}}, "download_checksums": {"https://raw.githubusercontent.com/openai/gpt-3/master/data/mid_word_1_anagrams.jsonl.gz": {"num_bytes": 106533, "checksum": "6768a86896083199de4815d4964cb2f6f1046476cfd80c2a562784f182905979"}}, "download_size": 106533, "post_processing_size": null, "dataset_size": 271516, "size_in_bytes": 378049}, "mid_word_2_anagrams": {"description": "Unscramble is a small battery of 5 \u201ccharacter manipulation\u201d tasks. Each task\ninvolves giving the model a word distorted by some combination of scrambling,\naddition, or deletion of characters, and asking it to recover the original word.\n", "citation": "@inproceedings{NEURIPS2020_1457c0d6,\n    author = {Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and Agarwal, Sandhini and Herbert-Voss, Ariel and Krueger, Gretchen and Henighan, Tom and Child, Rewon and Ramesh, Aditya and Ziegler, Daniel and Wu, Jeffrey and Winter, Clemens and Hesse, Chris and Chen, Mark and Sigler, Eric and Litwin, Mateusz and Gray, Scott and Chess, Benjamin and Clark, Jack and Berner, Christopher and McCandlish, Sam and Radford, Alec and Sutskever, Ilya and Amodei, Dario},\n    booktitle = {Advances in Neural Information Processing Systems},\n    editor = {H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin},\n    pages = {1877--1901},\n    publisher = {Curran Associates, Inc.},\n    title = {Language Models are Few-Shot Learners},\n    url = {https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf},\n    volume = {33},\n    year = {2020}\n}\n", "homepage": "https://github.com/openai/gpt-3/tree/master/data", "license": "", "features": {"context": {"dtype": "string", "id": null, "_type": "Value"}, "completion": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "unscramble", "config_name": "mid_word_2_anagrams", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"validation": {"name": "validation", "num_bytes": 282654, "num_examples": 10000, "dataset_name": "unscramble"}}, "download_checksums": {"https://raw.githubusercontent.com/openai/gpt-3/master/data/mid_word_2_anagrams.jsonl.gz": {"num_bytes": 109091, "checksum": "c3d839d09a7954b78a27cd2cd75d4ed0488656c56ef4dbd741a005343826cb01"}}, "download_size": 109091, "post_processing_size": null, "dataset_size": 282654, "size_in_bytes": 391745}, "cycle_letters_in_word": {"description": "Unscramble is a small battery of 5 \u201ccharacter manipulation\u201d tasks. Each task\ninvolves giving the model a word distorted by some combination of scrambling,\naddition, or deletion of characters, and asking it to recover the original word.\n", "citation": "@inproceedings{NEURIPS2020_1457c0d6,\n    author = {Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and Agarwal, Sandhini and Herbert-Voss, Ariel and Krueger, Gretchen and Henighan, Tom and Child, Rewon and Ramesh, Aditya and Ziegler, Daniel and Wu, Jeffrey and Winter, Clemens and Hesse, Chris and Chen, Mark and Sigler, Eric and Litwin, Mateusz and Gray, Scott and Chess, Benjamin and Clark, Jack and Berner, Christopher and McCandlish, Sam and Radford, Alec and Sutskever, Ilya and Amodei, Dario},\n    booktitle = {Advances in Neural Information Processing Systems},\n    editor = {H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin},\n    pages = {1877--1901},\n    publisher = {Curran Associates, Inc.},\n    title = {Language Models are Few-Shot Learners},\n    url = {https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf},\n    volume = {33},\n    year = {2020}\n}\n", "homepage": "https://github.com/openai/gpt-3/tree/master/data", "license": "", "features": {"context": {"dtype": "string", "id": null, "_type": "Value"}, "completion": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "unscramble", "config_name": "cycle_letters_in_word", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"validation": {"name": "validation", "num_bytes": 282654, "num_examples": 10000, "dataset_name": "unscramble"}}, "download_checksums": {"https://raw.githubusercontent.com/openai/gpt-3/master/data/cycle_letters_in_word.jsonl.gz": {"num_bytes": 98451, "checksum": "1689c9002bb8c5988bf5f05e977c9db92f57932c1b5a38998c29ac0dd71e1d42"}}, "download_size": 98451, "post_processing_size": null, "dataset_size": 282654, "size_in_bytes": 381105}, "random_insertion_in_word": {"description": "Unscramble is a small battery of 5 \u201ccharacter manipulation\u201d tasks. Each task\ninvolves giving the model a word distorted by some combination of scrambling,\naddition, or deletion of characters, and asking it to recover the original word.\n", "citation": "@inproceedings{NEURIPS2020_1457c0d6,\n    author = {Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and Agarwal, Sandhini and Herbert-Voss, Ariel and Krueger, Gretchen and Henighan, Tom and Child, Rewon and Ramesh, Aditya and Ziegler, Daniel and Wu, Jeffrey and Winter, Clemens and Hesse, Chris and Chen, Mark and Sigler, Eric and Litwin, Mateusz and Gray, Scott and Chess, Benjamin and Clark, Jack and Berner, Christopher and McCandlish, Sam and Radford, Alec and Sutskever, Ilya and Amodei, Dario},\n    booktitle = {Advances in Neural Information Processing Systems},\n    editor = {H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin},\n    pages = {1877--1901},\n    publisher = {Curran Associates, Inc.},\n    title = {Language Models are Few-Shot Learners},\n    url = {https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf},\n    volume = {33},\n    year = {2020}\n}\n", "homepage": "https://github.com/openai/gpt-3/tree/master/data", "license": "", "features": {"context": {"dtype": "string", "id": null, "_type": "Value"}, "completion": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "unscramble", "config_name": "random_insertion_in_word", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"validation": {"name": "validation", "num_bytes": 353981, "num_examples": 10000, "dataset_name": "unscramble"}}, "download_checksums": {"https://raw.githubusercontent.com/openai/gpt-3/master/data/random_insertion_in_word.jsonl.gz": {"num_bytes": 143626, "checksum": "72e65d83da53d15752ee0c47379509de149ddbad32d61184e5991df29616b78a"}}, "download_size": 143626, "post_processing_size": null, "dataset_size": 353981, "size_in_bytes": 497607}, "reversed_words": {"description": "Unscramble is a small battery of 5 \u201ccharacter manipulation\u201d tasks. Each task\ninvolves giving the model a word distorted by some combination of scrambling,\naddition, or deletion of characters, and asking it to recover the original word.\n", "citation": "@inproceedings{NEURIPS2020_1457c0d6,\n    author = {Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and Agarwal, Sandhini and Herbert-Voss, Ariel and Krueger, Gretchen and Henighan, Tom and Child, Rewon and Ramesh, Aditya and Ziegler, Daniel and Wu, Jeffrey and Winter, Clemens and Hesse, Chris and Chen, Mark and Sigler, Eric and Litwin, Mateusz and Gray, Scott and Chess, Benjamin and Clark, Jack and Berner, Christopher and McCandlish, Sam and Radford, Alec and Sutskever, Ilya and Amodei, Dario},\n    booktitle = {Advances in Neural Information Processing Systems},\n    editor = {H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin},\n    pages = {1877--1901},\n    publisher = {Curran Associates, Inc.},\n    title = {Language Models are Few-Shot Learners},\n    url = {https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf},\n    volume = {33},\n    year = {2020}\n}\n", "homepage": "https://github.com/openai/gpt-3/tree/master/data", "license": "", "features": {"context": {"dtype": "string", "id": null, "_type": "Value"}, "completion": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "unscramble", "config_name": "reversed_words", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"validation": {"name": "validation", "num_bytes": 282654, "num_examples": 10000, "dataset_name": "unscramble"}}, "download_checksums": {"https://raw.githubusercontent.com/openai/gpt-3/master/data/reversed_words.jsonl.gz": {"num_bytes": 91917, "checksum": "133a08f875cd6c1ef8608a3233571a773881cc27b1c707de738cc6543439332a"}}, "download_size": 91917, "post_processing_size": null, "dataset_size": 282654, "size_in_bytes": 374571}}